Surrogate Models for Stochastic Al-Cu Phase-Field Solidification
Simon Savukoski, Tatu Pinomaa
原文摘要
Phase-field models resolve microstructural evolution during rapid alloy solidification, but their computational cost limits long trajectories, stochastic ensembles, and studies across process conditions. We compare a deterministic U-Net with conditional flow matching (Flow), conditional diffusion (EDM), and a variance-preserving denoising diffusion bridge (VP-DDBM) for two-dimensional Al-Cu solidification. Given the current phase, concentration, and prescribed temperature fields, each model predicts the subsequent state and is applied autoregressively. At two thermal gradients outside the training range, we compare surrogate rollouts spanning \(48{,}000\) phase-field Euler steps with five phase-field futures generated from a common restart at each gradient. With two network evaluations per transition, Flow achieves the lowest time-averaged fair continuous ranked probability score among the generative surrogates for mean phase, mean Cu concentration, interface length, and leading-tip position at both gradients. Flow also reproduces the cellular morphology and retains sharp solid--liquid interfaces. It generates a single future approximately \(107\times\) faster than the phase-field solver on the reported hardware, showing potential for faster process-condition screening and ensemble-based microstructure studies.
cs.LG · cond-mat.mtrl-sci